Edge AI is increasingly being applied in embedded devices such as industrial cameras and public facility cameras, requiring embedded products to be compact and low power. The Renesas RZ/V series microprocessors (MPUs) come with a built-in AI accelerator, namely the Dynamic Reconfigurable Processor (DRP). This processor is known for its high energy efficiency, meeting the demands of the artificial intelligence market. This DRP technology has continuously evolved into DRP-AI3, providing higher AI inference performance than ever before.
Scan the QR code below or copy the link to view related information.
Dynamic Reconfigurable Processor (DRP)
https://www.renesas.cn/zh/key-technologies/artificial-intelligence/drp
Utilizing High-Performance MPU
Extending Battery Life and Creating Compact Products
The new RZ/V2N MPU is similar to the high-end RZ/V2H MPU (up to 80 TOPS) and is equipped with a high-efficiency AI accelerator DRP-AI3, achieving 10 TOPS/W AI performance through pruning technology, enhancing AI computational efficiency.
The image below (Figure 1) compares the AI inference performance of the traditional RZ/V series with the RZ/V2N. Taking the representative classification CNN Resnet50 as an example, the RZ/V2N performs 7 times better than the RZ/V2M without pruning (dense model), and 23 times better with pruning (90% pruning rate). This extremely high energy-efficient performance can extend battery life and eliminate the need for cooling fans, thus enabling device miniaturization.
Figure 1: Comparison of AI Inference Performance of RZ/V Series
Scan the QR code below or copy the link to view related information.
DRP-AI3
https://www.renesas.cn/zh/document/whp/next-generation-highly-power-efficient-ai-accelerator-drp-ai3-10x-faster-embedded-processing?r=25571164
Dual Camera Input
Can Improve AI-Based Image Recognition Accuracy
The RZ/V2N supports connecting two cameras through a dual-channel MIPI-CSI interface (Figure 2). Compared to traditional single-camera AI image recognition, this not only improves spatial recognition performance but also enables high-precision applications such as flow analysis and fall detection. For example, using dual-beam dual-angle imaging technology, it can monitor the number of parked cars and recognize license plates with a single chip.
In the Driver Monitoring System (DMS), the RZ/V2N can monitor and record the interior and exterior of the vehicle using a forward-facing camera and an in-cabin camera. Additionally, by configuring a stereo camera with two cameras, it can estimate the distance to the imaged object, thereby improving the AI camera and mobile robot’s AI-based image recognition accuracy.
Figure 2: Connecting Dual Cameras via Dual-Channel MIPI-CSI Interface
Highly Compatible with RZ/V2H Architecture
Reusable Design Resources
The RZ/V2N is similar to the RZ/V2H, equipped with a quad-core Arm® Cortex®-A55, a single-core Arm Cortex-M33, and an ISP (Image Signal Processor), allowing reuse of software development resources from RZ/V2H. Furthermore, due to the high compatibility of peripheral functions, users can choose the most suitable product from various RZ/V series MPUs based on their AI performance, system configuration, and real-time control requirements.
To enable users without deep AI expertise to quickly evaluate and develop AI applications, Renesas has released the RZ/V2N AI Software Development Kit. This kit includes Renesas evaluation board kits and software development environments, as well as over 50 different AI applications for various use cases. Utilizing this development environment can shorten time-to-market. Additionally, users with AI knowledge can choose the AI Compiler to develop their own AI models and integrate them into the RZ/V2N MPU (Figure 3).
Figure 3: Two Entry Points for AI Development Environment
Scan the QR code below or copy the link to view related information.
RZ/V2N AI Software Development Kit
https://www.renesas.cn/zh/software-tool/rzv2n-ai-software-development-kit
AI Compiler
https://www.renesas.cn/zh/key-technologies/artificial-intelligence/ai-tool-drp-ai-tvm
Additionally, Renesas ecosystem partners will successively provide products such as SOM (System on Module) boards, SBC (Single Board Computer), and camera modules using RZ/V2N. This allows users to free themselves from hardware design and focus on AI application development, enabling rapid product development.
This unique embedded AI processor RZ/V2N is the ideal choice for your next edge AI development. The device and its evaluation board (RZ/V2N-EVK) are available for purchase from the Renesas online store.
Visit the QR code below or copy the link to your browser for more detailed information.
More Detailed Information
www.renesas.com/rzv2n
* This product partially utilizes the results of projects commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
Need Technical Support?
If you have any questions while using Renesas MCU/MPU products, you can scan the QR code below or copy the URL into your browser to enter the Renesas Technical Forum to find answers or get online technical support.
https://community-ja.renesas.com/zh/forums-groups/mcu-mpu/
1
END
1
Recommended Reading
Q&A Win Prizes | 1min Quick Understanding of Renesas Capacitive Touch Technology
Winners Announced | Human-Machine Interface (HMI) Display and Touch Series Award List Released (First Issue)
elexcon 2025 | Renesas and Ecosystem Partners Present AI + Industrial Technology Showcase
